Paper: A Simple Word Trigger Method for Social Tag Suggestion

ACL ID D11-1146
Title A Simple Word Trigger Method for Social Tag Suggestion
Venue Conference on Empirical Methods in Natural Language Processing
Session Main Conference
Year 2011

It is popular for users in Web 2.0 era to freely annotate online resources with tags. To ease the annotation process, it has been great interest in automatic tag suggestion. We propose a method to suggest tags according to the text description of a resource. By consid- ering both the description and tags of a given resource as summaries to the resource written in two languages, we adopt word alignment models in statistical machine translation to bridge their vocabulary gap. Based on the translation probabilities between the words in descriptions and the tags estimated on a large set of description-tags pairs, we build a word trigger method (WTM) to suggest tags accord- ing to the words in a resource description. Experiments on real world datasets show that WTM is effective and robust compa...